LLM EXPLORER 60,783 MODELS INDEXED

Gemma 7B by google

By google · 29051 downloads
HF Repo ↗ Copy URL

Gemma 7B is an open-source language model by google. Features: 7b LLM, VRAM: 17.1GB, Context: 8K, License: gemma, Quantized, LLM Explorer Score: 0.28, Arc: 61.1, HellaSwag: 82.2, MMLU: 64.6, GSM8K: 50.9.

  Arxiv:1705.03551   Arxiv:1804.06876   Arxiv:1804.09301   Arxiv:1809.02789   Arxiv:1811.00937   Arxiv:1904.09728   Arxiv:1905.07830   Arxiv:1905.10044   Arxiv:1907.10641   Arxiv:1911.01547   Arxiv:1911.11641   Arxiv:2009.03300   Arxiv:2009.11462   Arxiv:2101.11718   Arxiv:2107.03374   Arxiv:2108.07732   Arxiv:2109.07958   Arxiv:2110.08193   Arxiv:2110.14168   Arxiv:2203.09509   Arxiv:2206.04615   Arxiv:2304.06364   Arxiv:2305.14314   Arxiv:2312.11805   Deploy:sagemaker   Endpoints compatible   Eval-results   Gemma   Gguf   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/google/gemma-7b 

Gemma 7B Parameters and Internals

Model Type 
text-to-text, decoder-only, large language models
Use Cases 
Areas:
Content Creation and Communication, Research and Education
Applications:
Text Generation, Chatbots and Conversational AI, Text Summarization, Natural Language Processing Research, Language Learning Tools, Knowledge Exploration
Primary Use Cases:
Question answering, Summarization, Reasoning
Limitations:
Biases from training data, Complex task handling limitations, Figurative language and nuances issues, Factual inaccuracies
Considerations:
Continuous monitoring, content safety guidelines, and education around privacy.
Supported Languages 
English (full)
Training Details 
Data Sources:
Web Documents, Code, Mathematics
Data Volume:
6 trillion tokens
Context Length:
8192
Hardware Used:
TPUv5e
Model Architecture:
text-to-text, decoder-only large language model
Safety Evaluation 
Methodologies:
structured evaluations, internal red-teaming
Findings:
acceptable thresholds for internal policies
Risk Categories:
Text-to-Text Content Safety, Text-to-Text Representational Harms, Memorization, Large-scale harm
Ethical Considerations:
Bias and Fairness, Misinformation, Transparency
Responsible Ai Considerations 
Fairness:
The model underwent input data pre-processing and evaluations to assess socio-cultural biases.
Transparency:
Summarizes details on architecture, capabilities, and limitations.
Accountability:
Open model development aims to share innovation with developers and researchers.
Mitigation Strategies:
De-biasing techniques, content safety mechanisms, and end-user education.
Input Output 
Input Format:
Text string
Accepted Modalities:
text
Output Format:
Generated English-language text
LLM NameGemma 7B
Repository 🤗https://huggingface.co/google/gemma-7b 
Base Model(s)  Gemma Ei Oc Structured Train   Holmeister/Gemma_ei_oc_structured_train
Model Size7b
Required VRAM17.1 GB
Updated2026-07-30
Maintainergoogle
Model Typegemma
Model Files  34.2 GB   5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureGemmaForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.38.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Quantized Models of the Gemma 7B

Model
Likes
Downloads
VRAM
Gemma 7B It12502494417 GB
Train060229 GB
Gemma 7B GGUF1521163 GB
CNCF0255 GB

Best Alternatives to Gemma 7B

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 7B It8K / 17.1 GB249441250
Gemma 1.1 7B It GGUF8K / 5.3 GB521
Train068K / 9.1 GB220
Llama2 Kazakh 7B GGUF8K / 4.1 GB100
Gemma 7B8K / 17.1 GB390
Gemma 7B Translator 0.48K / 17.1 GB390
Gemma 7B Translator 0.38K / 17.1 GB360
Gemma7B Konosuba8K / 17.1 GB201
Gemma 7B It GGUF8K / 5.3 GB611
Gemma 7B It GGUF8K / 3.1 GB45711
Note: green Score (e.g. "73.2") means that the model is better than google/gemma-7b.